CP SignalTechnology worth your attention.

Monday, 19 October 2026

The Daily Edition: 3 stories, ranked by significance

  1. Security & privacy

    Trojan Horse: Automated Repository Poisoning against Coding Agents

    Researchers introduce TrojanForge, described as the first automated framework for repository-level poisoning of coding agents, which uses AST analysis and adversarial refinement to hide malicious payloads. Tested against 384 poisoned repositories (TrojanBench) across 4 harnesses and 12 models, including commercial agents, the attack achieved over 60% poisoning success and over 90% backdoor injection, with even commercial agents failing to defend against it.

    Read the storyNo. 1 of 3arXiv cs.LGFri 16 Oct
  2. Artificial intelligence

    Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To

    A new arXiv paper finds that reasoning models show much higher chain-of-thought controllability when constraints are self-instructed inside the model's own reasoning rather than given as a standard user prompt, contradicting prior reports of very low controllability. The authors also demonstrate that this same self-instruction mechanism can be used to evade chain-of-thought monitoring setups, which they flag as a risk to using CoT for AI oversight.

    No. 2 of 3arXiv cs.LGFri 16 Oct
  3. Security & privacy

    When Core-Network Elements Become Reachable: Field-Level Exploitability Analysis in Diameter

    Researchers built LENS, a system that guides LLMs through the discipline and evidence-gathering practices of human security experts to analyze exploitability of the Diameter signaling protocol used in cellular core networks. The system found that over 25% of field paths in the S6a and Cx interfaces are exploitable, uncovering 95 previously unknown vulnerabilities in EPC/IMS implementations (17 open-source, 78 commercial), and a further 118 vulnerabilities when applied to 16 other protocols across cellular, network, industrial and host-internal systems.

    No. 3 of 3arXiv cs.LGFri 16 Oct